Analysing The Masked Predictive Coding Training Criterion For Pre-training A Speech Representation Model

Abstract

Recent developments in pre-trained speech representation utilizing self-supervised learning (SSL) have yielded exceptional results on a variety of downstream tasks. One such technique, known as masked predictive coding (MPC), has been employed by some of the most high-performing models. In this study, we investigate the impact of MPC loss on the type of information learnt at various layers in the HuBERT model, using nine probing tasks. Our findings indicate that the amount of content information learned at various layers of the HuBERT model has a positive correlation to the MPC loss. Additionally, it is also observed that any speaker-related information learned at intermediate layers of the model, is an indirect consequence of the learning process, and therefore cannot be controlled using the MPC loss. These findings may serve as inspiration for further research in the speech community, specifically in the development of new pre-training tasks or the exploration of new pre-training cri

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyyadav2023analysing

Related papers

• A Further Study Of Unsupervised Pre-training For Transformer Based Speech Recognition (2020)9.41
• Ms-hubert: Mitigating Pre-training And Inference Mismatch In Masked Language Modelling Methods For Learning Speech Representations (2024)4.52
• Supervision-guided Codebooks For Masked Prediction In Speech Pre-training (2022)7.81
• Predicting Within And Across Language Phoneme Recognition Performance Of Self-supervised Learning Speech Pre-trained Models (2022)0.00
• Progressive Residual Extraction Based Pre-training For Speech Representation Learning (2024)0.00
• Guided Contrastive Self-supervised Pre-training For Automatic Speech Recognition (2022)0.00
• Analyzing Speaker Information In Self-supervised Models To Improve Zero-resource Speech Processing (2021)9.23
• Hubert: Self-supervised Speech Representation Learning By Masked Prediction Of Hidden Units (2021)25.30